© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6504
    Prev
    Next
    INDEX
    Explanations

    the chemical composition of organic material or acids

    oai_token-act-pair · gemini-2.0-flash

    Technical or scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deauna
    -0.65
     kasarigan
    -0.63
     betweenstory
    -0.60
    횟
    -0.60
    }")
    
    -0.57
    belajaran
    -0.55
    subpackage
    -0.54
    "][
    -0.54
    '>";
    -0.53
    >(&
    -0.53
    POSITIVE LOGITS
    GraphicsUnit
    0.71
    
    0.57
     protoimpl
    0.57
    CodeAttribute
    0.56
    memoized
    0.55
    HomeAsUpEnabled
    0.55
    alisme
    0.54
    oneofs
    0.52
    VersionUID
    0.49
     UIKit
    0.49
    Activations Density 0.265%

    No Known Activations